© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13386
    Prev
    Next
    INDEX
    Explanations

    infrastructure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.87
     automatiques
    -0.83
     normaux
    -0.78
     métallique
    -0.77
     feroit
    -0.74
     avoient
    -0.74
     supérieurs
    -0.74
     garanzia
    -0.71
     juridiques
    -0.71
     fédé
    -0.71
    POSITIVE LOGITS
     development
    0.69
     building
    0.63
    building
    0.59
    build
    0.57
     creation
    0.55
     construction
    0.54
     roll
    0.53
     build
    0.51
     developing
    0.50
    development
    0.49
    Activations Density 0.009%

    No Known Activations